CN113510712A - Mechanical arm path planning method for transformer substation operation robot - Google Patents
Mechanical arm path planning method for transformer substation operation robot Download PDFInfo
- Publication number
- CN113510712A CN113510712A CN202110892374.9A CN202110892374A CN113510712A CN 113510712 A CN113510712 A CN 113510712A CN 202110892374 A CN202110892374 A CN 202110892374A CN 113510712 A CN113510712 A CN 113510712A
- Authority
- CN
- China
- Prior art keywords
- mechanical arm
- target
- switching operation
- path
- planning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000007689 inspection Methods 0.000 claims abstract description 47
- 230000033001 locomotion Effects 0.000 claims abstract description 14
- 238000000605 extraction Methods 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims abstract description 11
- 238000012423 maintenance Methods 0.000 claims description 20
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 5
- 230000007613 environmental effect Effects 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 10
- 230000008859 change Effects 0.000 description 6
- 230000004888 barrier function Effects 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000009529 body temperature measurement Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003702 image correction Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006996 mental state Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J18/00—Arms
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
- B25J19/021—Optical sensing devices
Abstract
The invention discloses a mechanical arm path planning method of a transformer substation operation robot, which solves the problem that only a mechanical arm for inspection cannot operate a switch cabinet in the prior art, and comprises the following steps: constructing a three-dimensional map of the transformer substation, and planning a routing inspection path of a mechanical arm; acquiring the current state of a transformer substation switch cabinet, and determining the target of switching operation; acquiring a three-dimensional coordinate point cloud of a target of switching operation by using a depth camera; accurately positioning the pose of the switching operation target by combining a three-dimensional point cloud target extraction algorithm; combining a motion planning algorithm to realize accurate switching operation on the target; judging whether the switching operation is in place, and if so, continuing to check according to the routing inspection path; if not, the process returns to step S3. The robot can realize multidimensional target operation of a button, a switch, a switching-on and switching-off device, an electrified display and a circuit protection device, and meanwhile, the robot can realize motion planning and obstacle avoidance algorithm, so that the robot can safely and efficiently operate to avoid obstacles on environmental equipment.
Description
Technical Field
The invention relates to the technical field of industrial mechanical arms, in particular to a mechanical arm path planning method for a transformer substation operation robot.
Background
The transformer substation is an important component of the power system, and has an extremely important position as a hub for converting voltage and transmitting electric energy in the power system. In an electric power system, switching operation is an operation for switching the operation state of electrical equipment, and is an essential operation link in traditional operation and maintenance. The traditional switching operation is realized by operating a distribution switch cabinet by professional electric power workers, and due to the restriction of a plurality of factors such as labor intensity, responsibility, service level, mental state and the like of operators, safety accidents are easy to occur during electrician operation, and serious losses are brought to power grid companies and people property. Therefore, the requirement for safe and stable operation of a modern transformer substation can not be met more and more by manual operation, and with the rise and development of technologies such as sensors, single-chip microcomputers, machine learning and robots, the intelligent robot is adopted to execute switching operation, so that the inevitable trend of intelligent power grid development is realized. The robot with complete functions and flexible operation is used for operating the power distribution cabinet, so that the control accuracy of the power distribution switch cabinet can be improved, the safety operation coefficient can be improved, the stability of power supply of a power grid enterprise to the society is guaranteed, the safety of the power grid and equipment of the power grid is guaranteed, and the robot has important functions and significance.
Therefore, the safety and the reasonability of the motion trail of the mechanical arm have important research significance, but most of the current researches are only mechanical arms with inspection functions, for example, the invention named as a path planning method for an overhead line maintenance mechanical arm is disclosed in 11.12.2020 by the Chinese patent office, the disclosure number of which is CN112060093A, the invention firstly obtains barrier information, an operation degree threshold value, initial position information of the tail end of the mechanical arm and terminal position information of the tail end of the mechanical arm, carries out non-collision path planning on the tail end position of the mechanical arm in a Cartesian space according to the barrier information, the operation degree threshold value, the initial position information of the tail end of the mechanical arm and the terminal position information of the tail end of the mechanical arm, provides a feasible path of the tail end of the mechanical arm, can avoid generating a large number of invalid sampling points, reduces the calculated amount, and then carries out secondary path planning, the secondary path planning of the invention can avoid the problem of difficult solution caused by excessive constraint consideration in the planning in the operation space until the feasible paths are connected, namely the whole path planning of the tail end of the mechanical arm is completed. But only inspection can be carried out, and switching operation cannot be executed.
Disclosure of Invention
The invention aims to provide a mechanical arm path planning method of a transformer substation operation robot, which is a design method of a switch cabinet switching operation mechanical arm based on a complex environment, integrates intelligent inspection and operation functions, can realize multi-dimensional target operation of a button, a switch, a switching-on/off device, a charged display and a line protection device based on multiple technologies such as accurate positioning, planar motion planning, force mode operation and the like, simultaneously realizes a motion planning and obstacle avoidance algorithm of the robot, ensures the safe and efficient operation of the robot, and realizes obstacle avoidance of environmental equipment.
In order to achieve the purpose, the invention adopts the following technical scheme: a mechanical arm path planning method for a transformer substation operation robot is characterized by comprising the following steps:
s1: constructing a three-dimensional map of the transformer substation, and planning a routing inspection path of a mechanical arm;
s2: acquiring the current state of a transformer substation switch cabinet, and determining the target of switching operation;
s3: acquiring a three-dimensional coordinate point cloud of a target of switching operation by using a depth camera;
s4: accurately positioning the pose of the target of the switching operation according to the three-dimensional coordinate point cloud obtained in the step S3 by combining a three-dimensional point cloud target extraction algorithm;
s5: combining a motion planning algorithm to realize accurate switching operation on the target;
s6: judging whether the switching operation is in place, and if so, continuing to check according to the routing inspection path; if not, the process returns to step S3.
In step S1, a three-dimensional map of the current environment is constructed, which may be constructed by acquiring environmental data using a binocular vision system at the front end of the robot arm, and an inspection path is obtained according to the constructed map, so that the robot arm can complete inspection. When the mechanical arm patrols and examines a switch cabinet which needs to be subjected to switching operation, firstly, state information of the current switch cabinet is obtained, whether the state information is consistent with that described in the instruction or not is judged, and then, according to the current state information and the state information which needs to be obtained after the switching operation, which device is to be operated is judged. And then, a three-dimensional coordinate point cloud of a target of switching operation is obtained by using a depth camera, the depth camera can identify the edge characteristics of the cabinet through depth data, then the plane of the cabinet is intercepted to judge the relative direction of the cabinet and the mechanical arm, and the mechanical arm is adjusted to reach the desired optimal shooting position according to the actual measured distance value. The reason why the three-dimensional point cloud target extraction algorithm is adopted in step S4 is that the three-dimensional point cloud obtained in step S3 has no object, and is only a stack of disordered three-dimensional points, and therefore extraction is required to obtain a complete three-dimensional map. The three-dimensional point cloud target extraction algorithm is a method based on global characteristics and a method based on local characteristics in the prior art. And then planning an operation path of the mechanical arm according to the obtained pose of the operation target, and executing switching operation by the mechanical arm. And after the execution is finished, judging whether the operation is in place, if not, executing again, and if so, continuing to perform the inspection work.
The intelligent inspection and operation integrated system integrates the intelligent inspection and operation functions, can accurately position, construct a mechanical arm inspection path, and can operate a barrier gate of a switch cabinet, so that the unmanned remote operation and maintenance management level of the transformer substation is enhanced, the integral operation and maintenance operation efficiency of the transformer substation is improved, the operation and maintenance cost is reduced, and the personal safety of operation and maintenance personnel is firmly guaranteed.
Preferably, the step S1 is further expressed as:
s1.1: acquiring binocular image data, routing inspection image data and three-dimensional point cloud data of the current environment, and accordingly constructing a three-dimensional map of the transformer substation;
s1.2: planning a mechanical arm inspection path and a mechanical arm moving path according to the information obtained in the step S1 and in combination with the inspection task;
s1.3: controlling the robot to move according to the path planned in the step S1.2, and acquiring binocular vision and three-dimensional laser sensor data in real time in the traveling process;
s1.4: driving the mechanical arm to move according to the mechanical arm moving path obtained in the step S1.2, and obtaining an image of the target inspection equipment through an image acquisition device;
s1.5: when the switch cabinet which needs switching operation is patrolled and examined, the mechanical arm is ready to operate the switch cabinet.
Patrol and examine and can let the arm carry on sensors such as visible light camera, infrared camera, partial discharge detector, carry out comprehensive perception and automatic monitoring to cubical switchboard running state. Therefore, when the mechanical arm is used for executing an inspection task, the mechanical arm can be used for inspecting along a specified line in a station and identifying the state of a switch cabinet target, including infrared target temperature measurement, cabinet meter reading identification, cabinet internal discharging condition monitoring and the like. When the mechanical arm patrols and examines, not only need to establish three-dimensional map according to the surrounding environment, the route is patrolled and examined to the planning department, also need simultaneously according to the position of mechanical arm and the position of the equipment of patrolling and examining, plans out the removal route of mechanical arm, because the high-order position of the equipment of patrolling and examining probably is different, and the mechanical arm needs to adjust in real time according to the condition. In the process of inspection operation, the mechanical arm is driven to move according to the position relation between the robot and the equipment to be inspected, the tail end image acquisition equipment of the mechanical arm faces to the position of the target equipment in the inspection process, the influence of the movement of the robot on image acquisition is compensated by adjusting the focal length, and the image of the target inspection equipment is acquired at the best shooting angle. When the switch cabinet needing switching operation is found, the mechanical arm stops, and the switch cabinet is ready to be switched.
Preferably, in the steps 1.3 and S1.4, if the robot arm collides with the environment during the inspection, the robot arm should stop, the three-dimensional map should be reconstructed, and the step S1 should be performed again. The obstacle avoidance of the environmental equipment is realized by ensuring the safe and efficient operation of the mechanical arm.
Preferably, in step S1.1, the image data includes: the starting position of the mechanical arm, the tail end position of the mechanical arm, the position of the equipment to be inspected and the joint angle of the mechanical arm. The starting position of the mechanical arm, the tail end position of the mechanical arm, the position of the inspected equipment and the joint angle of the mechanical arm are all related to the moving path of the mechanical arm, and the change of any data in the four data can cause the change of the moving path of the mechanical arm.
Preferably, the step S2 is further expressed as:
s2.1: acquiring image characteristics of the current power transformation cabinet by using an object identification method based on machine learning;
s2.2: comparing the obtained image characteristics with image information in a database, and judging which state the switch cabinet is in currently;
s2.3: and determining a target for switching operation according to the current state and the target state.
Judging which state the switch cabinet is in by comparing the image features of the current state with the image features of the four states in the database; and judging which device is to be operated according to the state after the switching operation, and determining the target.
Preferably, in step S2, the state of the switch cabinet includes: an operation state, a hot standby state, a cold standby state and a maintenance state; the goal of the switching operation includes: the state switching of the circuit protection device, the emergency opening and closing brake, the grounding switch, the handcart, the knob, the key and the auxiliary protection device.
The operation state refers to the state that primary equipment (here, a disconnecting switch and a circuit breaker; if the cabinet is removed, the high-voltage primary isolating contact and the secondary isolating contact are both switched on) in a certain loop is in a switching-on position, and a circuit from a power supply to a power receiving end is switched on, so that the operation state is presented. The hot standby state refers to a state in which the circuit breaker in a certain circuit is opened and the disconnecting switch (or the high-voltage primary isolating contact) is still in a closing position, and is a hot standby state. The cold standby state refers to a state that a circuit breaker and a disconnecting switch in a certain loop are both in an off position and is a cold standby state. The maintenance state means that the breaker and the disconnecting switch in a certain loop are both disconnected, and meanwhile, according to the relevant regulations of the technical measures for ensuring safety when the breaker and the disconnecting switch work on all or part of electrical equipment with power failure, a temporary grounding wire is hung (or a grounding disconnecting link is closed), a signboard is hung well, a temporary barrier is installed well, and the state of power failure maintenance is the maintenance state. The switching operation is to operate the object so as to change the electrical device from one state to another or to change the operation of the system.
Preferably, the step S3 is further expressed as:
s3.1: sensing the positions of the mechanical arm and the target of switching operation by using depth-of-field data of the depth camera, and stably capturing the target of switching operation by the mechanical arm to obtain a depth image;
s3.2: converting the depth image into a three-dimensional coordinate point cloud through a coordinate conversion formula, wherein the conversion formula is as follows:
wherein, x, y and z are point cloud coordinate systems, x 'and y' are depth image coordinate systems, and D is a depth value.
And obtaining a depth image by using a depth camera, and obtaining a three-dimensional coordinate point cloud from the depth image through coordinate conversion. Before coordinate transformation, image correction needs to be performed on the depth image.
Preferably, the step S5 is further expressed as:
s5.1: obtaining a random road map by utilizing a probability road map algorithm;
s5.2: and the mechanical arm realizes switching operation on the target according to the path diagram obtained in the step S5.1.
The probability road map algorithm is one of motion planning algorithms, and the motion planning algorithm is an algorithm for finding a path which meets constraint conditions for the mechanical arm between a given position A and a given position B, and comprises an artificial potential field method and a base sampling algorithm. The probabilistic roadmap algorithm is one of basic sampling algorithms, namely, N nodes are randomly selected in a planning space, then all the nodes are connected, and a connecting line contacting with an obstacle is removed, so that a stochastic roadmap is obtained. Other types of motion planning algorithms may also be employed with the present invention.
Preferably, in step S5, when the robot arm performs the switching operation according to the path diagram, the pressing and rotating operations are performed by using an anti-collision algorithm. The anti-collision algorithm is a prior art, and comprises an Aloha-based algorithm, also called a stochastic algorithm; tree-based algorithms, also known as deterministic algorithms; hybrid algorithm, an algorithm that is generated by combining an Aloha-based algorithm and a tree-based algorithm. The present invention may employ any of a variety of algorithms.
Preferably, the step S6 is further expressed as:
s6.1: after the operation of the mechanical arm is finished, acquiring the image characteristics of a target of the current switching operation by using an object recognition method based on machine learning;
s6.2: comparing the image characteristics obtained currently with the image characteristics in the state in the database, and judging whether the operation is in place;
s6.3: if the switching operation is not in place, returning to the step S3, and continuing to perform the switching operation on the target of the current switching operation.
If the current operation is not in place, switching operation needs to be carried out again, and the inspection work can not be continued until the operation is in place.
Therefore, the invention has the following beneficial effects: 1. the mechanical arm path planning method integrates intelligent routing inspection and operation functions, can finish routing inspection work and replace manual work, so that the mechanical arm can finish intelligent operation functions such as switching operation, protection device operation and the like; 2. the method is operated based on the image information, the information amount is rich, the calculation method is simple, the cost is low, and the method is easy to popularize; 3. the unmanned remote operation and maintenance management level of the transformer substation is enhanced, the integral operation and maintenance operation efficiency of the transformer substation is improved, the operation and maintenance cost is reduced, and a solid guarantee is provided for the personal safety of operation and maintenance personnel.
Drawings
FIG. 1 is a flow chart of the operation of the method of the present invention.
Detailed Description
The invention is described in further detail below with reference to the following detailed description and accompanying drawings:
as shown in fig. 1, an embodiment of a method for planning a path of a manipulator of a substation robot may be seen, where the method includes: constructing a three-dimensional map of the transformer substation, and planning a routing inspection path of a mechanical arm; acquiring the current state of a transformer substation switch cabinet, and determining the target of switching operation; acquiring a three-dimensional coordinate point cloud of a target of switching operation by using a depth camera; according to the three-dimensional coordinate point cloud obtained in the third step, combining a three-dimensional point cloud target extraction algorithm, and accurately positioning the pose of the target of switching operation; combining a motion planning algorithm to realize accurate switching operation on the target; judging whether the switching operation is in place, and if so, continuing to check according to the routing inspection path; if not, returning to the third step. When a three-dimensional map of the current environment is constructed, a binocular vision system at the front end of the mechanical arm can be adopted to collect environment data for construction, and an inspection path is obtained according to the constructed map, so that the mechanical arm can finish inspection operation. When the mechanical arm patrols and examines a switch cabinet which needs to be subjected to switching operation, firstly, state information of the current switch cabinet is obtained, whether the state information is consistent with that described in the instruction or not is judged, and then, according to the current state information and the state information which needs to be obtained after the switching operation, which device is to be operated is judged. And then, a three-dimensional coordinate point cloud of a target of switching operation is obtained by using a depth camera, the depth camera can identify the edge characteristics of the cabinet through depth data, then the plane of the cabinet is intercepted to judge the relative direction of the cabinet and the mechanical arm, and the mechanical arm is adjusted to reach the desired optimal shooting position according to the actual measured distance value. Because the three-dimensional point cloud obtained in the third step has no object, only a stack of disordered three-dimensional points is needed, and a complete three-dimensional image can be obtained only by extraction, a three-dimensional point cloud target extraction algorithm is adopted for extraction, and the pose of the operation target is obtained. Then, an operation path of the mechanical arm is planned, and the switching operation is executed by the mechanical arm. And after the execution is finished, judging whether the operation is in place, if not, executing again, and if so, continuing to perform the inspection work. Collect intelligence and patrol and examine and in an organic whole with operating function, can the accurate positioning, the arm is makeed and is patrolled and examined the route, can carry out the banister operation to the cubical switchboard simultaneously, has reinforceed the unmanned long-range fortune of transformer substation and has maintained the management level, has promoted the holistic fortune of transformer substation and has maintained the operating efficiency, has reduced fortune dimension cost, and the personal safety of more fortune dimension personnel provides solid guarantee.
The following further illustrates the technical solutions and effects of the present invention by means of specific examples.
The first step is as follows: building a three-dimensional map of the transformer substation and planning a routing inspection path of a mechanical arm
Acquiring binocular image data, routing inspection image data and three-dimensional point cloud data of the current environment, and accordingly constructing a three-dimensional map of the transformer substation; the image data includes: the starting position of the mechanical arm, the tail end position of the mechanical arm, the position of the equipment to be inspected and the joint angle of the mechanical arm. And planning a mechanical arm inspection path and a mechanical arm moving path according to the obtained information and in combination with the inspection task.
Controlling the robot to move according to the planned path, and acquiring binocular vision and three-dimensional laser sensor data in real time in the traveling process; since there may be a place where the constructed three-dimensional map is inconsistent in the actual environment, the three-dimensional map needs to be updated in real time.
Driving the mechanical arm to move according to the acquired mechanical arm moving path, and acquiring an image of the target inspection equipment through an image acquisition device; patrol and examine and can let the arm carry on sensors such as visible light camera, infrared camera, partial discharge detector, carry out comprehensive perception and automatic monitoring to cubical switchboard running state to make the arm when the task is patrolled and examined in the execution, the arm can be patrolled and examined along the appointed circuit in the station, carries out state identification to the cubical switchboard target, including infrared target temperature measurement, the internal meter reading of cabinet discernment and the internal portion condition monitoring of discharging etc.. In the process of inspection operation, according to the position relation between the robot and the equipment to be inspected, the mechanical arm is driven to move, so that the image acquisition equipment at the tail end of the mechanical arm faces to the position of target equipment, the influence of the movement of the robot on image acquisition is compensated by adjusting the focal length, and the image of the target inspection equipment is acquired at the optimal shooting angle; and automatically identifying the target based on the acquired image. If the mechanical arm collides with the environment in the inspection process, the mechanical arm needs to stop, a three-dimensional map is reconstructed, and the safe and efficient operation of the mechanical arm is guaranteed to realize obstacle avoidance on the environmental equipment.
When the switch cabinet which needs switching operation is patrolled and examined, the mechanical arm is ready to operate the switch cabinet.
The second step is that: obtaining the current state of the switch cabinet of the transformer substation, and determining the target of switching operation
The state of the switchgear comprises: an operation state, a hot standby state, a cold standby state and a maintenance state; the goal of the switching operation includes: the state switching of the circuit protection device, the emergency opening and closing brake, the grounding switch, the handcart, the knob, the key and the auxiliary protection device. The state of the switch cabinet comprises: an operation state, a hot standby state, a cold standby state and a maintenance state; the goal of the switching operation includes: the state switching of the circuit protection device, the emergency opening and closing brake, the grounding switch, the handcart, the knob, the key and the auxiliary protection device. The operation state refers to the state that primary equipment (here, a disconnecting switch and a circuit breaker; if the cabinet is removed, the high-voltage primary isolating contact and the secondary isolating contact are both switched on) in a certain loop is in a switching-on position, and a circuit from a power supply to a power receiving end is switched on, so that the operation state is presented. The hot standby state refers to a state in which the circuit breaker in a certain circuit is opened and the disconnecting switch (or the high-voltage primary isolating contact) is still in a closing position, and is a hot standby state. The cold standby state refers to a state that a circuit breaker and a disconnecting switch in a certain loop are both in an off position and is a cold standby state. The maintenance state means that the breaker and the disconnecting switch in a certain loop are both disconnected, and meanwhile, according to the relevant regulations of the technical measures for ensuring safety when the breaker and the disconnecting switch work on all or part of electrical equipment with power failure, a temporary grounding wire is hung (or a grounding disconnecting link is closed), a signboard is hung well, a temporary barrier is installed well, and the state of power failure maintenance is the maintenance state. The switching operation is to operate the object so as to change the electrical device from one state to another or to change the operation of the system.
The specific operation method comprises the following steps:
acquiring image characteristics of the current power transformation cabinet by using an object identification method based on machine learning;
comparing the obtained image characteristics with image information in a database, and judging which state the switch cabinet is in currently;
and determining a target for switching operation according to the current state and the target state.
The third step: obtaining a three-dimensional coordinate point cloud of a target of a switching operation using a depth camera
Sensing the positions of the mechanical arm and the target of switching operation by using depth-of-field data of the depth camera, and stably capturing the target of switching operation by the mechanical arm to obtain a depth image; converting the depth image into a three-dimensional coordinate point cloud through a coordinate conversion formula, wherein the conversion formula is as follows:
wherein, x, y and z are point cloud coordinate systems, x 'and y' are depth image coordinate systems, and D is a depth value.
And obtaining a depth image by using a depth camera, and obtaining a three-dimensional coordinate point cloud from the depth image through coordinate conversion. Before coordinate transformation, image correction needs to be performed on the depth image.
The fourth step: according to the three-dimensional coordinate point cloud obtained in the third step, combining a three-dimensional point cloud target extraction algorithm, accurately positioning the pose of the target of switching operation
The three-dimensional point cloud obtained in the third step has no object, only a group of scattered three-dimensional points needs to be extracted to obtain a complete three-dimensional image, and therefore the three-dimensional point cloud target extraction algorithm is adopted for extraction to obtain the accurate pose of the operation target.
The fifth step: combining with a motion planning algorithm to realize accurate switching operation on the target
Obtaining a random road map by utilizing a probability road map algorithm; and the mechanical arm realizes switching operation on the target according to the path diagram obtained in the step S5.1, and when the mechanical arm performs switching operation according to the path diagram, the anti-collision algorithm is used for realizing pressing and rotating operation. The probability map algorithm and the anti-collision algorithm are both the prior art, and are used for constructing a path map from the mechanical arm to an operation target and changing the path in real time when the mechanical arm operates, so that the mechanical arm can accurately complete switching operation.
And a sixth step: judging whether the switching operation is in place, and if so, continuing to check according to the routing inspection path; if not, go back to the third step
After the operation of the mechanical arm is finished, acquiring the image characteristics of a target of the current switching operation by using an object recognition method based on machine learning; then, comparing the image characteristics obtained at present with the image characteristics in the database in the state, and judging whether the operation is in place; if the current switching operation is not in place, returning to the step S3, and continuing to perform the switching operation on the target of the current switching operation. Collect intelligence and patrol and examine and operate function in an organic whole, can accomplish the work of patrolling and examining, can replace the manual work again, make the arm accomplish intelligent operation functions such as switching operation, protection device operation.
The above-described embodiments are only preferred embodiments of the present invention, and are not intended to limit the present invention in any way, and other variations and modifications may be made without departing from the spirit of the invention as set forth in the claims.
Claims (10)
1. A mechanical arm path planning method for a transformer substation operation robot is characterized by comprising the following steps:
s1: constructing a three-dimensional map of the transformer substation, and planning a routing inspection path of a mechanical arm;
s2: acquiring the current state of a transformer substation switch cabinet, and determining the target of switching operation;
s3: acquiring a three-dimensional coordinate point cloud of a target of switching operation by using a depth camera;
s4: accurately positioning the pose of the target of the switching operation according to the three-dimensional coordinate point cloud obtained in the step S3 by combining a three-dimensional point cloud target extraction algorithm;
s5: switching operation is realized on the target by combining a motion planning algorithm;
s6: judging whether the switching operation is in place, and if so, continuing to check according to the routing inspection path; if not, the process returns to step S3.
2. The method for planning the path of a manipulator of a substation operation robot according to claim 1, wherein the step S1 is further represented as:
s1.1: acquiring binocular image data, routing inspection image data and three-dimensional point cloud data of the current environment, and accordingly constructing a three-dimensional map of the transformer substation;
s1.2: planning a mechanical arm inspection path and a mechanical arm moving path according to the information obtained in the step S1 and in combination with the inspection task;
s1.3: controlling the robot to move according to the path planned in the step S1.2, and acquiring binocular vision and three-dimensional laser sensor data in real time in the traveling process;
s1.4: driving the mechanical arm to move according to the mechanical arm moving path obtained in the step S1.2, and obtaining an image of the target inspection equipment through an image acquisition device;
s1.5: when the switch cabinet which needs switching operation is patrolled and examined, the mechanical arm is ready to operate the switch cabinet.
3. The mechanical arm path planning method for the substation operation robot according to claim 2, wherein in the step 1.3 and the step S1.4, if the mechanical arm collides with the environment in the inspection process, the mechanical arm needs to be stopped, the three-dimensional map is reconstructed, and the step S1 is performed again.
4. The method for planning the path of the manipulator of the substation operation robot according to claim 2, wherein in step S1.1, the image data includes: the starting position of the mechanical arm, the tail end position of the mechanical arm, the position of the equipment to be inspected and the joint angle of the mechanical arm.
5. The method for planning the path of a manipulator of a substation operation robot according to claim 1, wherein the step S2 is further expressed as:
s2.1: acquiring image characteristics of the current power transformation cabinet by using an object identification method based on machine learning;
s2.2: comparing the obtained image characteristics with image information in a database, and judging which state the switch cabinet is in currently;
s2.3: and determining a target for switching operation according to the current state and the target state.
6. The method for planning the path of a manipulator of a substation operation robot according to claim 1 or 5, wherein in step S2, the state of the switch cabinet comprises: an operation state, a hot standby state, a cold standby state and a maintenance state; the goal of the switching operation includes: the state switching of the circuit protection device, the emergency opening and closing brake, the grounding switch, the handcart, the knob, the key and the auxiliary protection device.
7. The method for planning the path of a manipulator of a substation operation robot according to claim 1, wherein the step S3 is further expressed as:
s3.1: sensing the positions of the mechanical arm and the target of switching operation by using depth-of-field data of the depth camera, and then stably capturing the target of switching operation to obtain a depth image;
s3.2: converting the depth image into a three-dimensional coordinate point cloud through a coordinate conversion formula, wherein the conversion formula is as follows:
wherein, x, y and z are point cloud coordinate systems, x 'and y' are depth image coordinate systems, and D is a depth value.
8. The method for planning the path of a manipulator of a substation operation robot according to claim 1, wherein the step S5 is further expressed as:
s5.1: obtaining a random road map by utilizing a probability road map algorithm;
s5.2: and the mechanical arm realizes switching operation on the target according to the path diagram obtained in the step S5.1.
9. The method for planning the path of the mechanical arm of the substation operation robot according to claim 1 or 8, wherein in the step S5, when the mechanical arm performs switching operation according to the path diagram, an anti-collision algorithm is used to realize precise operation.
10. The method for planning the path of a manipulator of a substation operation robot according to claim 1, wherein the step S6 is further represented as:
s6.1: after the operation of the mechanical arm is finished, acquiring the image characteristics of a target of the current switching operation by using an object recognition method based on machine learning;
s6.2: comparing the image characteristics obtained currently with the image characteristics in the state in the database, and judging whether the operation is in place;
s6.3: if the switching operation is not in place, returning to the step S3, and continuing to perform the switching operation on the target of the current switching operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110892374.9A CN113510712A (en) | 2021-08-04 | 2021-08-04 | Mechanical arm path planning method for transformer substation operation robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110892374.9A CN113510712A (en) | 2021-08-04 | 2021-08-04 | Mechanical arm path planning method for transformer substation operation robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113510712A true CN113510712A (en) | 2021-10-19 |
Family
ID=78068182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110892374.9A Pending CN113510712A (en) | 2021-08-04 | 2021-08-04 | Mechanical arm path planning method for transformer substation operation robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113510712A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114012694A (en) * | 2021-11-19 | 2022-02-08 | 国网上海市电力公司 | Trackless intelligent robot capable of automatically operating and maintaining and control method thereof |
| CN116852350A (en) * | 2023-06-09 | 2023-10-10 | 中煤陕西榆林能源化工有限公司 | Control method and device for switching operation, storage medium and electronic equipment |
| CN117061876A (en) * | 2023-10-11 | 2023-11-14 | 常州微亿智造科技有限公司 | Fly-swatter control method and system based on fly-swatter robot |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102255392A (en) * | 2011-07-30 | 2011-11-23 | 山东电力研究院 | Method for controlling switching operation sequences of full-automatic transformer substation based on mobile robot |
| US20160195390A1 (en) * | 2015-01-05 | 2016-07-07 | Bell Helicopter Textron Inc. | Inspecting components using mobile robotic inspection systems |
| CN105870814A (en) * | 2016-03-31 | 2016-08-17 | 广东电网有限责任公司中山供电局 | Emergency breaking operation device suitable for 10kV switch |
| CN107206592A (en) * | 2015-01-26 | 2017-09-26 | 杜克大学 | Special purpose robot's motion planning hardware and production and preparation method thereof |
| CN206598277U (en) * | 2016-08-31 | 2017-10-31 | 杭州申昊科技股份有限公司 | A kind of crusing robot |
| CN107367672A (en) * | 2017-07-20 | 2017-11-21 | 国网江西省电力公司电力科学研究院 | High-tension switch cabinet Full-automatic belt electro-detection method and device |
| US20170341231A1 (en) * | 2016-05-31 | 2017-11-30 | General Electric Company | Systems and methods for control of robotic manipulation |
| CN107443355A (en) * | 2017-08-04 | 2017-12-08 | 国网山东省电力公司电力科学研究院 | A kind of mechanical arm and control method for partial discharge of switchgear detection |
| CN207223953U (en) * | 2017-07-20 | 2018-04-13 | 国网江西省电力公司电力科学研究院 | A kind of multi-functional live detection robot of high-tension switch cabinet |
| CN208044007U (en) * | 2018-04-03 | 2018-11-02 | 湖北南邦创电科技有限公司 | Cubicle switch cabinet Partial Discharge Detection robot of substation |
| CN110303468A (en) * | 2019-05-24 | 2019-10-08 | 广东电网有限责任公司 | A kind of double bodies machinery people local operation high-voltage circuit-breaker switching on-off method and system |
| CN210774139U (en) * | 2019-06-05 | 2020-06-16 | 广西电网有限责任公司电力科学研究院 | Inspection robot system capable of comparing internal temperature and external temperature of switch cabinet |
| CN111958591A (en) * | 2020-07-30 | 2020-11-20 | 国网智能科技股份有限公司 | Autonomous inspection method and system for semantic intelligent substation inspection robot |
| CN111958593A (en) * | 2020-07-30 | 2020-11-20 | 国网智能科技股份有限公司 | Vision servo method and system for inspection operation robot of semantic intelligent substation |
| CN111985420A (en) * | 2020-08-25 | 2020-11-24 | 北京奥特雷柏科技有限公司 | Power distribution station unmanned inspection method based on machine vision |
| CN112947298A (en) * | 2021-03-24 | 2021-06-11 | 合肥工业大学 | Method, system and terminal for optimally generating curved surface machining track of robot |
-
2021
- 2021-08-04 CN CN202110892374.9A patent/CN113510712A/en active Pending
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102255392A (en) * | 2011-07-30 | 2011-11-23 | 山东电力研究院 | Method for controlling switching operation sequences of full-automatic transformer substation based on mobile robot |
| US20160195390A1 (en) * | 2015-01-05 | 2016-07-07 | Bell Helicopter Textron Inc. | Inspecting components using mobile robotic inspection systems |
| CN107206592A (en) * | 2015-01-26 | 2017-09-26 | 杜克大学 | Special purpose robot's motion planning hardware and production and preparation method thereof |
| CN105870814A (en) * | 2016-03-31 | 2016-08-17 | 广东电网有限责任公司中山供电局 | Emergency breaking operation device suitable for 10kV switch |
| US20170341231A1 (en) * | 2016-05-31 | 2017-11-30 | General Electric Company | Systems and methods for control of robotic manipulation |
| CN206598277U (en) * | 2016-08-31 | 2017-10-31 | 杭州申昊科技股份有限公司 | A kind of crusing robot |
| CN207223953U (en) * | 2017-07-20 | 2018-04-13 | 国网江西省电力公司电力科学研究院 | A kind of multi-functional live detection robot of high-tension switch cabinet |
| CN107367672A (en) * | 2017-07-20 | 2017-11-21 | 国网江西省电力公司电力科学研究院 | High-tension switch cabinet Full-automatic belt electro-detection method and device |
| CN107443355A (en) * | 2017-08-04 | 2017-12-08 | 国网山东省电力公司电力科学研究院 | A kind of mechanical arm and control method for partial discharge of switchgear detection |
| CN208044007U (en) * | 2018-04-03 | 2018-11-02 | 湖北南邦创电科技有限公司 | Cubicle switch cabinet Partial Discharge Detection robot of substation |
| CN110303468A (en) * | 2019-05-24 | 2019-10-08 | 广东电网有限责任公司 | A kind of double bodies machinery people local operation high-voltage circuit-breaker switching on-off method and system |
| CN210774139U (en) * | 2019-06-05 | 2020-06-16 | 广西电网有限责任公司电力科学研究院 | Inspection robot system capable of comparing internal temperature and external temperature of switch cabinet |
| CN111958591A (en) * | 2020-07-30 | 2020-11-20 | 国网智能科技股份有限公司 | Autonomous inspection method and system for semantic intelligent substation inspection robot |
| CN111958593A (en) * | 2020-07-30 | 2020-11-20 | 国网智能科技股份有限公司 | Vision servo method and system for inspection operation robot of semantic intelligent substation |
| CN111985420A (en) * | 2020-08-25 | 2020-11-24 | 北京奥特雷柏科技有限公司 | Power distribution station unmanned inspection method based on machine vision |
| CN112947298A (en) * | 2021-03-24 | 2021-06-11 | 合肥工业大学 | Method, system and terminal for optimally generating curved surface machining track of robot |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114012694A (en) * | 2021-11-19 | 2022-02-08 | 国网上海市电力公司 | Trackless intelligent robot capable of automatically operating and maintaining and control method thereof |
| CN116852350A (en) * | 2023-06-09 | 2023-10-10 | 中煤陕西榆林能源化工有限公司 | Control method and device for switching operation, storage medium and electronic equipment |
| CN116852350B (en) * | 2023-06-09 | 2024-02-13 | 中煤陕西榆林能源化工有限公司 | Control method and control device for switching operation |
| CN117061876A (en) * | 2023-10-11 | 2023-11-14 | 常州微亿智造科技有限公司 | Fly-swatter control method and system based on fly-swatter robot |
| CN117061876B (en) * | 2023-10-11 | 2024-02-27 | 常州微亿智造科技有限公司 | Fly-swatter control method and system based on fly-swatter robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113510712A (en) | Mechanical arm path planning method for transformer substation operation robot | |
| CN108890657B (en) | Intelligent inspection robot for power distribution room | |
| CN104977930B (en) | High pressure same tower double back transmission line unmanned plane inspection barrier-avoiding method based on electric field strength change rate | |
| CN102280826B (en) | Intelligent robot inspection system and intelligent robot inspection method for transformer station | |
| CN109861387B (en) | Intelligent inspection system for transformer substation | |
| CN103235562A (en) | Patrol-robot-based comprehensive parameter detection system and method for substations | |
| EP3840217A1 (en) | Methods for mapping power generation installations | |
| WO2011100409A1 (en) | Line inspection robot and system | |
| CN103605365A (en) | Fully automatic operation method of substation equipment pollution inspection, determination and cleaning | |
| KR102056564B1 (en) | Method And Apparatus for Managing Facility by using Machine Vision | |
| CN114859972A (en) | Inspection system and method for cooperative operation of aerial unmanned aerial vehicle and ground inspection robot | |
| CN113708491A (en) | Intelligent inspection system for traction substation | |
| CN102930408B (en) | A kind of 750kV electric grid secondary equipment state appraisal procedure based on information fusion | |
| Guo et al. | A patrol robot for electric power substation | |
| CN110497416A (en) | A kind of trouble-shooter of switchgear | |
| CN114115317A (en) | Substation unmanned aerial vehicle inspection method based on artificial intelligence | |
| CN113111714A (en) | Risk prevention and control system applied to power transmission field operation | |
| CN112269397A (en) | Unmanned aerial vehicle inspection method based on high-precision positioning and visual tracking | |
| CN208172191U (en) | A kind of pressing plate switch condition intelligent detection identification device system | |
| Xiao-le et al. | 500 kV substation robot patrol system | |
| CN115291598A (en) | Route planning method based on industrial grade 5G inspection robot | |
| CN114696250A (en) | Intelligent operation and maintenance robot and method for switch cabinet of power distribution room | |
| CN111913182B (en) | Substation operation and detection robot and electrified region isolation method thereof | |
| Li et al. | Intelligent control method of live working robot based on cloud and edge computing terminal | |
| CN112706172A (en) | Remotely controllable robot for a power distribution station |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211019 |